.png){kind=icon}
.png){kind=icon}
Return
ACTIONABLE LEARNING ANALYTICS: PREDICTING UNIVERSITY PERFORMANCE LEVELS WITH INTERPRETABLE MACHINE LEARNING
.png){kind=icon}
PRE
AI
DOI：10.7160/eriesj.2026.190102.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Higher education institutions need timely, explainable tools to identify students at risk of performance on large-scale examinations and to guide targeted academic support strategies. In response to this challenge, this study proposes an explainable machine learning framework to predict undergraduate students' performance levels in Colombia's SABER PRO examination. Using student background variables (e.g., gender, region, school type, parental education, occupation) and SABER 11 standardised test scores (Critical Reading, Mathematics, Citizenship Skills, Science, and English), we formulate a binary classification problem that distinguishes desirable outcomes (levels 3-4) from non-desirable outcomes (levels 1-2). We benchmark baseline models against non-linear learners, including XGBoost, GLMNET, SVM, DT, and LDA, using fold cross-validation protocol with systematic hyperparameter tuning. Model performance assessed through confusion matrices and AUC scores. To support educational decision-making, complement predictive results with explainability analyses, including global feature importance and individual-level explanations via SHAP, enabling transparent identification of the key drivers behind performance levels. The proposed approach provides actionable learning analytics to guide early academic support, promote responsible and transparent educational decision-making, improve the likelihood of desirable SABER PRO achievement.
Keywords:
Academic performance
explainable artificial intelligence
learning analytics
Journal
J
IF:
1.3
Papers:
7
Citations:
0